Methods and apparatus to adjust content presented to an individual

Abstract

Methods, apparatus, systems and articles of manufacture to adjust content presented to an individual are disclosed. An example system includes a first modality sensor to measure a first response of an individual to first content during a first time frame and a second modality sensor to measure a second response of the individual to the first content during the first time frame. The first modality sensor is to measure a third response of the individual to first content during a second time frame, and the second modality sensor is to measure a fourth response of the individual to the first content during the second time frame. The example system also includes a mental classifier executing instructions to determine a first mental classification of the individual based on a first comparison of the first response to a first threshold and a second comparison of the second response to a second threshold. The mental classifier also is to determine a second mental classification of the individual based on a third comparison of the third response to a third threshold and a fourth comparison of the fourth response to a fourth threshold. In addition, the mental classified is to determine a mental state of the individual based on a degree of similarity between the first mental classification and the second mental classification. The example system also includes a content modifier to at least one of modify the first content to include second content or replace the first content with second content based on the mental state.

Description

RELATED APPLICATIONS

This patent arises from a continuation of U.S. patent application Ser. No. 15/155,543, titled “METHODS AND APPARATUS TO ADJUST CONTENT PRESENTED TO AN INDIVIDUAL,” and filed on May 16, 2016, which claims priority to U.S. Provisional Application No. 62/163,874, titled “MULTI-PHASIC EMOTION AND COGNITION CLASSIFIERS,” filed on May 19, 2015, and to U.S. Provisional Application No. 62/272,423, titled “METHODS AND APPARATUS TO ADJUST CONTENT PRESENTED TO AN INDIVIDUAL,” filed on Dec. 29, 2015. U.S. patent application Ser. No. 15/155,543; U.S. Provisional Application No. 62/163,874; and U.S. Provisional Application No. 62/272,423 are hereby incorporated herein by reference in their entireties. Priority to U.S. patent application Ser. No. 15/155,543; U.S. Provisional Application No. 62/163,874; and U.S. Provisional Application No. 62/272,423 is hereby claimed.

FIELD OF THE DISCLOSURE

This disclosure relates generally to presenting content to an individual and, more particularly, to methods and apparatus to adjust content presented to an individual.

BACKGROUND

Individuals are exposed to multiple passive and interactive audio, visual, and audio-visual media content every day. The media content produces biologically based responses in the user that can be measured by one or more sensors. An individual's biological and/or physical response to an image can indicate emotional and cognitive responses. Personal logs and self-reporting of responses are often inaccurate and include biases due to human input. Additionally, personal logs and self-reporting rely on an accurate account by the individual of their own emotional and cognitive reaction.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a schematic illustration of an example system in which an example content presentation device constructed in accordance with the teachings of this disclosure is implemented.

FIG. 2 is a block diagram of an example system that may be used to implement one or more of the example devices of the example system of FIG. 1.

FIG. 3 is a representation of an example mental classification grid that may be used by the example content presentation device of FIGS. 1 and/or 2 to adjust content presented to an individual.

FIG. 4 is a representation of an example mental classification matrix that may be used by the example content presentation device of FIGS. 1 and/or 2 to adjust content presented to an individual.

FIG. 5 is a representation of overlapping time windows that may be used by the example content presentation device of FIGS. 1 and/or 2 to adjust content presented to an individual.

FIG. 6 is a flowchart representative of example machine-readable instructions for adjusting content presented to an individual that may be executed by the example systems of FIGS. 1 and/or 2.

FIG. 7 is a flowchart representative of example machine-readable instructions for adjusting a baseline and/or threshold that may be executed by the example systems of FIGS. 1 and/or 2.

FIG. 8 is a block diagram of an example processor platform structured to execute the example machine-readable instructions of FIGS. 6 and 7 implemented by the example systems of FIGS. 1 and/or 2.

The figures are not to scale. Wherever possible, the same reference numbers will be used throughout the drawing(s) and accompanying written description to refer to the same or like parts.

DETAILED DESCRIPTION

Many different kinds of media content, such as audio, visual, and audio-visual content are presented to individuals every day. The presentation of media content to the individual can result in a biologically based response in the individual, which can be used to determine a mental state of the user. For example, a user may be frustrated or confused by media content displayed by a website, including the website interface, a game, etc. Data related to a particular determined mental state of a user may be used, for example, in marketing applications. For example, if a user exhibits a biological response indicative of frustration caused by a website design, the user may be less likely spend time on the website and purchase products from the business owner of the website. Thus, market researchers could use the information about determined mental states of users to adapt the website to provide a more enjoyable experience to a user and potential consumer as indicated by positive mental or emotional states detected through the biological responses. Users having enjoyable and pleasant experiences are more likely to spend more time on a website and may be more likely to purchase products and/or services. In some examples, the media content (e.g., the website) may adapt automatically based on the determined mental state of the individual.

Example apparatus and methods described herein adjust content (e.g., media content such as commercial advertisements, websites, videos, Internet content, etc.) presented to an individual based on a determined mental state (e.g., frustration, concentration, boredom, etc.) of the individual. The mental state of the individual is determined based on measured responses (e.g., biometric responses such as heart rate, pupil dilation, etc.) to presented content. In some examples, the responses of the individual are measured using modality sensors (e.g., sensors to measure biometric responses such as heart rate sensors, pressure sensors, facial expression detectors or facial action coding (FAC), etc.) and compared to respective thresholds to determine response classifications (e.g., high or low heart rate; high, medium, or low pupil dilation; etc.).

In some examples, the thresholds may correspond to a baseline (e.g., a threshold amount above a baseline) associated with the response of the individual over a period of time during presentation of the content. For example, the measured response of an individual over time may be used to develop a baseline of biometric response activity. In such examples, an individual may have biometric data recorded while exposed to neutral or background media (as opposed to a targeted media or stimulus). The baseline determines the level of biometric activity of the person in, for example, an inactive or uninvolved state. This determination of the baseline may be different from individual to individual because, for example, some individuals have higher resting heart rates than others or different rates of respiration, etc. A threshold is set to indicate when, for example, an individual response indicative of excitement is high enough relative to the baseline to register as a positive response. Thus, the biometric data may be compared to the individualized threshold(s) to determine a high or low classification on a moment-by-moment basis for each subject, panelist, or user. Furthermore, in this example, the baseline is used as a reference for the threshold. If the comparison of the signal (the biometric data) to the threshold is constantly resulting in a “low” or “high” classification, for example, the baseline and, in some instance also the threshold, are adjusted because the response of the individual has changed over time and is not being accurately represented or detected by the constantly “low” or “high” classification. In other words, the fluctuations or changes in the individual's response may not be detected because the measured responses consistently remain below the threshold and, therefore, the threshold and baseline are to be changed to capture the fluctuations or changes.

In another example in which the baseline is adjusted based on the measured responses, a baseline is increased when a measured response is consistently higher than the threshold because this indicates that the response of the individual has changed. In this example, the baseline is increased after a period of time (e.g., thirty seconds) to account for the shift in the response of the individual (i.e., the fluctuations of the response of the individual are better measured if the baseline and threshold are increased). For example, if an individual has a resting heart rate of 70 beats per minute (bpm) (e.g., a baseline measurement), the threshold for a “high” heart rate classification may be 75 bpm. If the individual is frustrated, the heart rate may rise by, for example, approximately 10 bpm and, thus, be consistently classified as “high.” In this example, when the baseline is held at 70 bpm and the threshold is held at 75 bpm, the fluctuations of the heart rate between 77 bpm and 85 bpm are not detected because the entire signal between 75 bpm and 85 bpm is registered as “high.” Thus, changing the baseline and the threshold to more accurately represent the new baseline heart rate of the individual enables the fluctuations at the higher heart rate range to be classified as high or low with respect to the new baseline and threshold.

Additionally or alternatively, the baseline and/or threshold may be changed based on the task being performed by the individual. For example, a simple task (e.g., shopping for a toothbrush) may result in little or no change to the baseline and/or threshold, but a more complex task (e.g., configuring a car) may result in a larger change to the baseline and/or threshold. In some examples, the length of time the task is estimated to take may affect the adjustment of the baseline and/or threshold.

The response classifications measured during a first time frame may be combined to determine a mental classification (e.g., concentration, frustration, confusion, etc.). For example, the response classifications of high GSR, high pupil dilation, high negative FAC, and low positive FAC may indicate, when combined, that the individual is actively engaged and has a mental classification of frustration. In some examples, the mental classification is determined by, for example, combining response classifications corresponding to responses measured by different modality sensors (e.g., two or more different sensors). For example, a low GSR response, a low pupil dilation, a low negative FAC, and a low positive FAC may be combined to indicate a mental classification of low and/or no engagement (boredom). In some examples, a second mental classification is determined based on additional responses measured during a second time frame. A mental state is designated if consecutive mental classifications are similar (e.g., the mental state is designated based on a degree of similarity between consecutive mental classifications). In some examples, the mental state indicates a reaction of the individual to the presented content (e.g., frustration, confusion, etc.). In such examples, the content is adjusted or new content (e.g., second content), different from the content originally presented (e.g., first content), is presented to the individual to increase the positivity level of the reaction.

In the examples disclosed herein, the responses are measured during overlapping time frames to ensure that no peak measurements (e.g., a peak galvanic skin response (GSR) measurement) are missed. For example, the first time frame begins when the content is presented to the individual and the second time frame begins prior to an end of the first time frame. In some such examples, each time frame has a duration of four seconds and the second time frame begins one second after the first time frame begins. In conventional methods in which discrete windows are used, a peak that occurs at the end of one window and into the next may be lost.

In some examples, the response classifications are combined in time segments that include multiple overlapping time frames. For example, if each time frame has a duration of four seconds, the time segments may have a duration of two seconds. In such examples, the time segments include responses from up to four different time frames. In some examples, a mental classification is determined for each time segment based on the response classification corresponding to the respective time segments. In some such examples, the mental state is designated if the mental classifications for consecutive time segments (e.g., two or more consecutive segments) are similar. Alternatively, no mental state is designated if no consecutive mental classifications are similar.

Disclosed in some examples herein, are methods to adjust content presented to an individual. The example method includes measuring, via a first modality sensor, a first response of the individual to first content during a first time frame and determining a first response classification based on a first comparison of the first response and a first threshold. The example method also includes measuring, via a second modality sensor, a second response of the individual to the first content during the first time frame and determining a second response classification based on a second comparison of the second response to a second threshold. In addition, the example method includes determining a first mental classification of the individual based on combining the first response classification and the second response classification and determining a first baseline during the first time frame, at least one of the first threshold or second threshold based on the first baseline. The example method includes measuring, via the first modality sensor, a third response of the individual to first content during a second time frame and measuring, via the second modality sensor, a fourth response of the individual to the first content during the second time frame. In addition, the method includes adjusting the first baseline to a second baseline based on at least one of the third response or the fourth response in the second time frame, adjusting at least one of the first threshold to a third threshold or second threshold to a fourth threshold based on the second baseline, determining a third response classification based on a third comparison of the third response and the third threshold, and determining a fourth response classification based on a fourth comparison of the fourth response and the fourth threshold; determining a second mental classification of the individual based on combining the third response classification and the fourth response classification. Other aspects of the example method include determining a mental state of a user based on a degree of similarity between the first mental classification and the second mental classification, and at least one of modifying the first content to include second content or replacing the first content with second content based on the mental state.

In some examples, the first modality sensor includes a galvanic skin response sensor. Also, in some examples, the second modality sensor includes a pupil dilation sensor.

In some examples, the method also includes generating a cognitive load index based on data from the pupil dilation sensor. The cognitive load index is representative of how much of a maximum information processing capacity of the individual is being used.

In some example methods, the second time frame partially overlaps the first time frame.

In some examples, the method includes measuring, via a third modality sensor, a fifth response of the individual to the first content during the first time frame and determining a fifth response classification based on a fifth comparison of the fifth response and a fifth threshold, the first mental classification of the individual based on combining the first response classification and the second response classification further with the fifth response classification. The method also includes measuring, via the third modality sensor, a sixth response of the individual to the first content during the second time frame, and determining a sixth response classification based on a sixth comparison of the sixth response and the fifth threshold, the second mental classification of the individual based on combining the third response classification and the fourth response classification further with the sixth response classification.

In some examples, the third modality sensor includes a facial action coding sensor. Also, in some examples, the third modality sensor includes an eye tracking sensor.

Also, in some examples disclosed herein, the second content is to increase a positivity level of the mental state. In addition, in some examples, the second content is to at least one of induce a purchase or increase a total spend amount on a purchase.

Also disclosed herein are example systems including, a system that includes a first modality sensor, a second modality sensor, and a processor. In the example system, the processor is to measure, via the first modality sensor, a first response of an individual to first content during a first time frame and determine a first response classification based on a first comparison of the first response and a first threshold. The example processor also is to measure, via the second modality sensor, a second response of the individual to the first content during the first time frame, and determine a second response classification based on a second comparison of the second response to a second threshold. The example system also uses the processor to determine a first baseline during the first time frame, at least one of the first threshold or second threshold based on the first baseline and determine a first mental classification of the individual based on combining the first response classification and the second response classification. In addition, the processor is to measure, via the first modality sensor, a third response of the individual to first content during a second time frame, measure, via the second modality sensor, a fourth response of the individual to the first content during the second time frame, adjust the first baseline to a second baseline based on at least one of the third response or the fourth response in the second time frame, and adjust at least one of the first threshold to a third threshold or the second threshold to a fourth threshold based on the second baseline. Other determinations are also made by the example processor including, for examples, determining a third response classification based on a third comparison of the third response and the third threshold, determining a fourth response classification based on a fourth comparison of the fourth response to the fourth threshold, determining a second mental classification of the individual based on combining the third response classification and the fourth response classification, and determining a mental state of a user based on a degree of similarity between the first mental classification and the second mental classification. In addition, the example system uses the processor to at least one of modify the first content to include second content or replace the first content with second content based on the mental state.

Also disclosed herein are tangible computer readable storage media comprising instructions that, when executed, causes a processor of a content presentation device to at least measure, via a first modality sensor, a first response of an individual to first content during a first time frame, determine a first response classification based on a first comparison of the first response and a first threshold, measure, via a second modality sensor, a second response of the individual to the first content during the first time frame, and determine a second response classification based on a second comparison of the second response to a second threshold. In these examples, the instructions further cause the machine to determine a first baseline during the first time frame, at least one of the first threshold or second threshold based on the first baseline, and determine a first mental classification of the individual based on combining the first response classification and the second response classification. In addition, executing the instructions also causes the machine to measure, via the first modality sensor, a third response of the individual to first content during a second time frame, measure, via the second modality sensor, a fourth response of the individual to the first content during the second time frame, adjust the first baseline to a second baseline based on the third response or the fourth response in the second time frame, and adjust at least one of the first threshold to a third threshold or the second threshold to a fourth threshold based on the second baselines. Furthermore, in this example, the machine is caused by the executed instructions to determine a third response classification based on a third comparison of the third response and the third threshold, determine a fourth response classification based on a fourth comparison of the fourth response to the fourth threshold, determine a second mental classification of the individual based on combining the third response classification and the fourth response classification, and determine a mental state of a user based on a degree of similarity between the first mental classification and the second mental classification. Also, in this example, the machine is to at least one of modify the first content to include second content or replace the first content with second content based on the mental state.

Further disclosed herein are systems such as an example system that includes a first modality sensor to measure a first response of an individual to first content during a first time frame. The example system also includes a second modality sensor to measure a second response of the individual to the first content during the first time frame. The first modality sensor is to measure a third response of the individual to first content during a second time frame, and the second modality sensor is to measure a fourth response of the individual to the first content during the second time frame. The example system includes a response classifier to determine a first response classification based on a first comparison of the first response and a first threshold and determine a second response classification based on a second comparison of the second response to a second threshold. In addition, the example system includes a baseline generator to determine a first baseline during the first time frame, at least one of the first threshold or second threshold based on the first baseline and adjust the first baseline to a second baseline based on at least one of the third response or the fourth response in the second time frame. The baseline generator also is to adjust at least one of the first threshold to a third threshold or the second threshold to a fourth threshold based on the second baseline. In addition, the response classifier is to further determine a third response classification based on a third comparison of the third response and the third threshold and determine a fourth response classification based on a fourth comparison of the fourth response to the fourth threshold. The example system also includes a mental classifier to determine a first mental classification of the individual based on combining the first response classification and the second response classification and determine a second mental classification of the individual based on combining the third response classification and the fourth response classification. The mental classifier also is to determine a mental state of a user based on a degree of similarity between the first mental classification and the second mental classification. The example system also includes a content modifier to at least one of modify the first content to include second content or replace the first content with second content based on the mental state.

In some examples, the system further includes a third modality sensor to measure a fifth response of the individual to the first content during the first time frame and measure a sixth response of the individual to the first content during the second time frame. Also, in such example systems, the response classifier is to determine a fifth response classification based on a fifth comparison of the fifth response and a fifth threshold, and the mental classifier is to base the first mental classification of the individual on combining the first response classification and the second response classification further with the fifth response classification. In addition, the response classifier is to determine a sixth response classification based on a sixth comparison of the sixth response and the fifth threshold, and the mental classifier is to base the second mental classification of the individual on combining the third response classification and the fourth response classification further with the sixth response classification.

Turning now to the figures, FIG. 1 is a schematic illustration of an example system 100 in which an example content presentation device 102 is implemented. In some examples, the example system 100 is implemented in a laboratory environment for monitoring an individual 104. In other examples, the system 100 may be implemented in other environments including, for example, a public location or a private residence.

In the illustrated example system 100, the content presentation device 102 is a desktop computer. In other examples, the content presentation device 102 may be any device suitable to present media content to an individual 104, such as a television, a radio, an Internet-streamed audio source, a workstation, a kiosk, a laptop computer, a tablet computer, an e-reader, a smartphone, etc. The example content presentation device 102 presents media content to the individual 104 that includes audio, visual, and/or audio-visual content. In some examples, the content is advertisement(s) and/or entertainment. Also, in some examples, the content is interactive, such as a video game, live interaction, or an Internet experience (e.g., a website). The example content presentation device 102 includes a display 106 and/or an audio output 108 (e.g., speakers, a headset) to present the media content to the individual 104. In some examples, the display 106 and/or the audio output 108 enables the individual 104 to interact with the content presentation device 102. The content presentation device 102 includes one or more of a keyboard 110, a mouse 112, a touchscreen, a microphone, a remote control, etc. to facilitate an interaction between the individual 104 and the content presentation device 102.

In some examples, the content presentation device 102 is used to measure and/or record self-reported responses, such as responses to computer generated surveys, text input, and/or audio responses. Self-reported measurements include, but are not limited to, survey responses to items such as perception of the experience, perception of the usability or likeability of the experience, level of personal relevance to user, attitude toward content or advertising embedded in the content, intent to purchase a product, game, or service, and changes in responses from before and after testing.

In some examples, the input devices (e.g. the mouse 112 and/or keyboard 110 and/or other input devices) include sensors (e.g., biometric sensors, pressure sensors) to measure a response of the individual 104. For example, interactive content is presented to the individual 104 according to a predefined program or sequence biometric response data is recorded and synchronized or mapped to the content presentation to indicate what biological response the individual 104 had to what portion of the presentation.

As shown in FIG. 1, the additional input devices of the example system 100 include one or more modality sensors, such as sensors 114, 116, 118, to monitor a reaction of the individual 104 to the presented content. In some examples, the modality sensors 114, 116, 118 are communicatively coupled to the example content presentation device 102. Alternatively, one or more of the modality sensors 114, 116, 118 are integrated with the example content presentation device 102. The modality sensors include one or more of a camera 114 and/or biometric sensors, such as biometric sensing clothing 116 and a biometric sensing bracelet 118. In some examples, the camera 114 is a video camera and/or an infrared camera. The modality sensors 114, 116, 118 are operative to measure, for example, any combination of eye tracking responses, behavioral responses, and/or other biological responses. In some examples, eye tracking responses include pupil dilation, saccadic motion, gaze location (e.g., direction of attention) and duration, and iris size. In some examples, behavioral responses include facial expressions, levels of vocalized emotion (e.g., measure of stress of the individual 104) and movement. The detected facial expressions express discrete emotions on the face, such as joy, surprise, confusion, sadness, etc. In some examples, the biological responses include heart rate (HR) (e.g., camera-based heart rate measurement), galvanic skin response (GSR) (a measure of skin conductivity), neural activity (EEG), respiration, blood flow in the prefrontal cortex (detected by near infrared spectroscopy), activity in specific brain areas (e.g., as determined by functional MRI), skin temperature, other body temperatures, blood pressure, EMG, etc.

In some examples, the measured response data is linked and/or synchronized with the content presentation using time stamps and/or event windows. For example, the presentation is divided into event windows based on specific tasks or activities that are included in the interactive content presented to the individual 104, and the measured response data is associated with the event windows based on the tasks or activities. In some examples, each task or activity has one or more event windows associated with the task or activity. Additionally, each event window can be the same or a different duration of time as the other event windows.

The one or more modality sensors 114, 116, 118 and/or the content presentation device 102 are in communication with a server 120 via a wired or wireless network 122. In some examples, the sensors 114, 116, 118 are coupled to the network 122 via the content presentation device 102. In some examples, the network 122 uses communication technologies such as RS-232, Ethernet, Wi-Fi, Bluetooth or ZigBee. The server 120 additionally is in communication with a results analyzing device 124, which is illustrated as a desktop computer but other devices may be used as noted herein. Additionally or alternatively, more than one communication technology is used at the same time, including wired components (e.g., Ethernet, digital cable, etc.) and wireless components (Wi-Fi, WiMAX, Bluetooth, etc.) to connect the sensors 114, 116, 118 and/or other computer system components to the server 120.

Alternatively or additionally, the results analyzing device 124 includes any device suitable to analyze data collected by the content presentation device 102 and/or the modality sensors 114, 116, 118, including a workstation, a kiosk, a laptop computer, a tablet computer, and a smartphone. In some examples, the results analyzing device 124 receives input from a reviewer 126 related to the results corresponding to the individual 104. The results are transmitted to, for example, the server 120, a second server, and/or an additional computing device. Alternatively, the results include a generated report 128 (e.g., a hard or a soft copy) distributed to, for example, a client. In some examples, the results analyzing device 124 is integrated with the content presentation device 102 to determine moment-to-moment, event-to-event or total level of emotion and cognition classifiers and provides the results to the server 120. Analyzing the results using the results analyzing device 124 prior to transmitting the results the server 120 decreases the amount of data transferred, resulting in faster data processing and lower transmission bandwidth requirements to increase the operating efficiency of the system.

As used herein, the phrase “in communication,” including variances thereof, encompasses direct communication and/or indirect communication through one or more intermediary components and does not require direct physical (e.g., wired) communication and/or constant communication, but rather additionally includes selective communication at periodic or aperiodic intervals, as well as one-time events.

FIG. 2 is a block diagram of an example system 200 that may be used to implement one or more of the example devices of the example system 100 of FIG. 1. The example system 200 includes a mental state determination module 202. The example mental state determination module 202 determines a mental state of the individual 104 based on measured responses to content presented to the individual 104.

The example mental state determination module 202 is communicatively coupled to a plurality of modality sensors including, for example, a first modality sensor 204, a second modality sensor 206, and an Nth modality sensor 208. In some examples, the first modality sensor 204, the second modality sensor 206, and the Nth modality sensor 208 correspond to any of the camera 114, the biometric sensing clothing 116, and the biometric bracelet 118 of FIG. 1. Alternatively, the first, second, and Nth modality sensors 204, 206, and 208 include any sensor operative to measure at least one of an eye tracking response, a behavioral response, or a biometric response of the individual 104. Additional modality sensors may be included to measure other biometric responses of the individual.

The example mental state determination module 202 includes an input/output interface (I/O interface) 210. The example I/O interface 210 is operatively coupled to the first, second, and Nth modality sensors 204, 206, and 208 to communicate a response of the individual 104 to the example mental state determination module 202. Additionally or alternatively, the I/O interface 210 is operatively coupled to any of the display 106, the audio output 108, the keyboard 110, the mouse 112, a touchscreen, a microphone, or any other device capable of providing an output to the individual 104 and/or providing an input to the content presentation device 102. Additionally, the I/O interface 210 is in communication with the server 120 of FIG. 1 to communicate with the example results analyzing device 124 and/or any other device in communication with the server 120. For example, the I/O interface 210 receives the content to be presented to the individual 104 via communication with the server 120. Alternatively or additionally, the I/O interface 210 transmits results from the content presentation device 102 to the server 120.

In the illustrated example, the mental state determination module 202 includes storage 212 (e.g., a mass storage device) to store response data corresponding to the individual 104, content to be presented to the individual 104, and/or instructions for processing the response data. The example storage 212 is in communication with the I/O interface 210 to send and receive response data and/or media content to and/or from, for example, the first modality sensor 204, the second modality sensor 206, the Nth modality sensor 208, and/or the server 120. Alternatively or additionally, in some examples, the example storage 212 is in direct communication with one or more of the first modality sensor 204, the second modality sensor 206, the Nth modality sensor 208, and the server 120.

The example mental state determination module 202 includes a response classifier 214 to determine a response classification of measured response data received from one or more of the first, second, and Nth modality sensors 204, 206, and 208. The example response classifier 214 determines the response classification (e.g., high or low heart rate; high or low GSR; high, medium, or low pupil dilation; etc.) by, for example, comparing the measured response to a threshold. In some examples, each measured response corresponding to one of the modality sensors 204, 20, 208 is compared to a different threshold (e.g., a respective threshold) based on, for example, different biological characteristics of the signals and responses for the respective modality. The threshold is determined based on, for example, an average value of the measured response during an initial time period (e.g., a baseline). In some examples, the response classifier 214 determines which responses are most likely to be relevant to the mental state of the individual 104 from the available response measurements. In some examples, the selection of responses relevant to the mental state is confirmed using a research methodology. For example, a hypothesis is generated, a study is created, participants are recruited, data is collected and analyzed, and a conclusion is drawn. Additionally or alternatively, in some examples, a statistical model of the contributions of each of the responses is created to select the responses with the greatest relevance to the mental state of the individual 104. The example statistical model may be used to classify responses and/or determine a range for characterization of responses using an assumed statistical probability density. In some examples, the statistical model may form the bases for classification barriers and determine if one mental state is more likely than another.

The example mental state determination module 202 includes an example bin classifier 216. In some examples, the bin classifier 216 creates one or more bins in which to place each response based on the respective thresholds and/or a baseline. For example, each response (e.g., the measurement from each modality sensor 204, 206, 208) is sorted into a bin (e.g., a high bin, a low bin) based on the comparison to the threshold, and the one or more bins may be created based on the baseline. In some examples, the bin classifier 216 determines binning criteria based on the response measurement and/or sensor measuring the response being binned. For example, for GSR binning, the baseline (e.g., the binning criteria) is determined by calculating a mean GSR for a portion of the response measurement. Example GSR bins include a high bin (e.g., 50% increase above the mean GSR) and a low bin (e.g., 25% increase above the mean GSR). Additionally or alternatively, binning criteria for an HR response measurement is determined by a change in absolute beats-per-minute (bpm) within a two-second window. Example HR bins include a high bin (e.g., increase of 12-15 bpm) and a low bin (e.g., decrease of 12-15 bpm).

Additionally or alternatively, the bin classifier 216 divides some responses, such as facial responses, into positive and negative categories prior to sorting the response into a high or low bin. In such examples, a database of facial responses is created from participants during testing to determine relative baseline(s) for positive and negative expressions. Example facial response bins include a high bin (e.g., one standard deviation in probability of coding an expression as positive/negative above the standard deviation and the opposite response is low (i.e., to code high positive FAC, negative FAC response must be low)) and a low bin (e.g., one standard deviation decrease in probability, below data baseline, of coding an expression as positive/negative).

In some examples, the bin classifier 216 creates an intermediate bin for response measurements, such as pupil dilation. For example, pupil dilation binning includes determining the baseline based on a function of change from mean pupil dilation during some portion of the measured response. In some examples, pupil dilation binning includes a medium bin to capture times when the individual 104 is cognitively engaged, but not necessarily heavily concentrating, frustrated, or bored. Example pupil dilation bins include a high bin (e.g., mean dilation plus at least one half standard deviation), a medium bin (e.g., within one half standard deviation of the mean), and a low bin (e.g., mean dilation minus at least one half standard deviation). In some examples, the response classifier 214 uses the bins to determine the response classification of a response and/or places the responses in bins based on the comparison of the response to the threshold. In some such examples, the response classifier 214 and the bin classifier 216 work cooperatively to place responses in an appropriate bin based on the response classification and/or the comparison of the response to the threshold or baseline.

Typically, all responses are weighted equally when determining the mental state of the individual 104 (e.g., if three responses were measured, each response contributes to the mental state 33%). In some examples, the responses are weighted by adjusting the contribution of one or more responses to the overall results to be more or less than the contribution of other responses. For example, if one of the modality sensors 204, 206, 208 is not measuring data for all or part of the content presentation, the weighting of the contribution of each response is adjusted (e.g., if only two responses are measured at a given time, each response contributes to the mental state 50%). As more response data is collected and/or as the reaction to the presented content changes, the weights of the responses contributions can be adjusted to improve accuracy of the results (e.g., the response classification, a mental classification, the determined mental state).

The example mental state determination module 202 includes an example baseline generator 218. In some examples, the baseline generator 218 determines an initial baseline using a baselining procedure. For example, response measurements are not binned (e.g., classified) for an initial time period such as, for example, thirty seconds. The length of the initial time period may vary based on a task being performed by the individual. In some examples, neutral content is presented to the individual 104 during the initial time period. During the initial time period, a representative value (e.g., a mean value, a standard deviation, etc.) is determined by the baseline generator 218, for example, for the responses related to each sensor and are used as the initial baseline. In such examples, responses are compared to the initial baseline and/or a respective one of the thresholds. Additionally or alternatively, after the initial time period, the baseline is periodically adjusted based on the measured responses. For example, the baseline generator 218 re-evaluates the baseline for each baseline time period (e.g., thirty seconds) and adjusts the baseline based on the response. Alternatively or additionally, the baseline time period is the same as the first time frame. For example, if a user's GSR is above the mean (e.g., sorted in the high bin) for a period of time and then drops below the mean, the baseline determiner 218 adjusts the baseline in response to the drop in the GSR measurement to establish a new baseline. Thus, the baseline determiner 218 automatically adjusts the baseline corresponding to each response measurement in response to the occurrence of relevant events.

Automatically adjusting the baseline as the response of the individual changes and/or develops increases the accuracy of the determined mental state. For example, determining the mental state based on a single and/or constant baseline may not detect fluctuations or changes in the response of the individual (e.g., drop in heart rate after a period of higher heart rate) because the response (e.g., heart rate) may still be higher than the initial baseline and, thus, classified as high. The failure to detect these fluctuations or changes may result in an incorrect classification of the response.

In addition, there are many advantages to adjusting the baseline. For example, if an individual is experiencing frustration with a website, which is detected based on the individual's GSR being above a threshold relative to the baseline, and there may be a modification of the content to alter the mental state of the user to a more enjoyable experience. The modification of the content may begin to work to bring the individual to a less frustrated state. However, at the initial stages of the change, the individual's GSR may remain above the threshold relative to the baseline, though the individual's mental state is changing in accordance with the goals of the modified content. However, these changes may go undetected based on the level of GSR compared to the threshold relative to the baseline. Whereas, an adjusted baseline would change the threshold trigger, and enable detection of the GSR (in this example) moving across the threshold and provide indication that the content modification is effective. Therefore, the content modification can continue to bring the individual into the desired mental state. In addition, where the baseline is moved and the threshold has not been triggered though content has been modified, the operator or website owner would know that the content modification did not work (or did not work fast enough) or that a secondary baseline adjustment may be needed for a finer detection of biometric responses and/or mental classification and state changes.

In some examples, a running window implementation is used. In some such examples, the running windows include overlapping time windows (e.g., four-second windows). In some examples, the responses are measured using overlapping windows to avoid inaccuracies and/or missed events in the collected data. For example, GSR measurements typically peak at approximately four to five seconds, which can be missed or misinterpreted using non-overlapping time windows to measure GSR responses. In the example disclosed herein, the time windows each have a duration of four seconds and begin in one-second increments. In other examples, any other suitable or desired time duration(s) and/or increment(s) may be used. In some examples, the response is binned and/or a response classification is determined for each of the time windows.

The example mental state determination module 202 also includes an example mental classifier 220. The example mental classifier 220 determines mental classifications related to the measured responses (e.g., raw data from the modality sensors) and/or the response classifications (e.g., response data that is classified based on a threshold). In some examples, the mental classifications are determined by combining response classifications (e.g., high heart rate and low GSR) corresponding to one or more modality sensors 204, 206, and 208. In the illustrated example, the response classifications are combined in time segments shorter than the time windows (e.g., two seconds) and include the response classifications determined for each time window related to the time segment.

In some examples, the mental classifier 220 uses a mental classification grid, such as the example mental classification grid 300 in FIG. 3, to determine a mental classification for a time segment based on the one or more response classifications associated with the time segment. FIG. 3 is a representation of an example mental classification grid 300 that may be used by the example systems of FIGS. 1 and/or 2 to adjust content presented to an individual 104. In the illustrated example, the mental classification grid 300 includes three axes (e.g., cognitive load 302, emotional valence 304, and emotional arousal 306). In other examples, the classification grid 300 includes more than three axes (e.g., four axes, five axes, etc.).

In some examples, one of the axes used to determine a mental classification of an individual is cognitive load. The cognitive load axis 302 refines the classifications and/or the emotional valence 304 and the emotional arousal 306. The cognitive load is determined based on biological measures, such as measurements of pupil dilation. A cognitive load index represents the maximum amount of information the individual 104 can process at a given time. Cognitive load 302 is quantified based on the index to represent how much information the individual 104 is processing at a given time. Including cognitive load 302 as an axis in the example mental classification grid 300 provides significant functionality. Each individual 104 is determined to have a maximum information processing capacity. Comparing the cognitive load of the individual 104 during a period of time to the cognitive load index provides information related to the mental state of the individual 104. For example, if the individual 104 exhibits a high cognitive load index and a low emotional index, the determined mental state is concentration. In some examples, the emotional index is based on the emotional valence 304 and/or the emotional arousal 306. Thus, the use of cognitive load 302 allows the example mental state determination module 202 and/or the mental classifier 220 to distinguish between mental states such as frustration, confusion, and concentration.

Additionally or alternatively, the mental classifier 220 uses a mental classification matrix, such as the example mental classification matrix 400 of FIG. 4, to determine a mental classification based on one or more response classifications. FIG. 4 is a representation of an example mental classification matrix 400 that is used by the example system of FIGS. 1 and/or 2 to adjust content presented to an individual 104. The example classification matrix 400 represents an example method of combining example response classifications 402 to determine example mental classifications 404. In the illustrated example mental classification matrix 400, the example response classifications 402 represent possible combinations of response classifications for a response measurement. For example, a first response measurement may occur during a first time window (e.g., time window 502 of FIG. 5) and correspond to high GSR, high positive FAC, and low negative FAC, which are combined by, for example, the example mental classifier 220 to produce the mental classification of active engagement (positive). Other mental classifications are created by combining different response classifications 402 for similar response measurements.

In the illustrated example, response classifications 402 that can be combined by the mental classifier 220 to create other mental classifications 404 (e.g., active engagement (frustration), active concentration (flow state), passive concentration, low/no engagement (boredom), etc.) include one or more response classifications 402 different than the response classifications 402 combined to provide an active engagement (positive) mental classification 404. The example response classifications 402 in the example mental classifications matrix 400 include response classifications 402 corresponding to measurements (e.g., GSR, pupil dilation, FAC, etc.) using the sensors (e.g., the first modality sensor 204, the second modality sensor 206, the Nth modality sensor 208, the camera 114, the biometric sensing clothing 116, the biometric sensing bracelet 118, etc.). In other examples, the example response classifications 402 correspond to additional and/or alternative sensor measurements (e.g., HR, EEG, pupil tracking, etc.). The example mental classification matrix 400 illustrated in FIG. 4 represents only a portion of the potential response classifications 402 and/or mental classifications 404 that can be designated as the mental state of the individual and, thus, the mental state and/or the mental classifications 404 are not limited to the example mental classifications 404 in the mental classification matrix 400 of FIG. 4.

FIG. 5 is a representation of overlapping time windows 502-510 used by the example system of FIGS. 1 and/or 2 to adjust content presented to an individual 104. The example time windows 502-510 correspond to response measurements from a single modality sensor such as, for example the first modality sensor 204. In some examples, the first time window 502 begins when the content is presented to the individual 104. In some examples, each of the subsequent time windows 504-510 begin one second after the previous time window (e.g., each time window 504-510 begins in a one-second interval). For example, the first time window 502 begins at time 0:00:00, as shown by the timeline 512, a second time window 504 begins at time 0:00:01, and a third time window 506 begins at time 0:00:02. Alternatively, the time windows 502-510 begin at different intervals determined based on, for example, the length of each of the time windows 502-510 and/or the length of each of the segments 514-520. In some examples, the response measurements from the other sensors (e.g., the second modality sensor 206, the Nth modality sensor 208, etc.) have time windows of the same duration as the length of the time windows 502-510. Additionally or alternatively, the time windows 502-510 correspond to a response classification for the response measurement. For example, the example response classifier 214 determines a response classification for the response measurements in each of the time windows 502-510.

In some examples, the example response classifications corresponding to time windows 502-510 are combined in two-second time segments 514-520 to determine a mental classification for each of the time segments 514-520. In some examples, the response measurements from all modality sensors 204, 206, 208 are combined during the same time segment (e.g., time segment 514) to determine a mental classification corresponding to the time segment 514. Additionally or alternatively, the time windows 502-510 falling within each of the time segments 514-520 are combined to determine the mental classification for a time segment (e.g., time segment 516). For example, the mental classification corresponding to time segment 516 is determined by combining response classifications from all time windows (e.g., the first four time windows 502-508) that at least partially overlap and/or fall within the time segment 516. In the illustrated example of FIG. 5, the time segments 514-520 include four different mental classifications (e.g., positive active, negative active, positive passive, and negative passive) and no mental state of the individual 104 is designated. Alternatively, one or more consecutive time segments include a similar mental classification (e.g., segments 514-516 are positive active) and a mental state of the individual 104 is designated based on the similar mental classification.

In some examples, the mental classifier 220 (FIG. 2) selects relevant responses (e.g., response measurements likely to be indicative of the mental state of the individual 104) used to determine the mental classification of the individual 104. In some examples, additional responses of the individual 104 are measured for the first time frame during which content is presented to the individual 104. In such examples, an additional response classification is determined based on a comparison of the additional response measured to an additional threshold. In some such examples, the additional response classification is combined with the first response classification. In such examples, the first mental classification is altered based on the additional response classification.

After the mental state determination module 202 determines the mental state of the individual 104, an example content modifier 222 determines whether to modify the content. In some examples, the content modifier 222 edits the content presented to the individual 104 based on the determined mental state of the individual 104. For example, if the mental state indicates that the individual 104 is frustrated, the content modifier 222 presents new content (e.g., second content) to the individual and/or adjusts the content to increase a positivity of the mental state. In some examples, the new content includes a coupon and/or a video (e.g., a tutorial video). Alternatively, the new content is a coupon, a free gift, a suggestion, etc. In some such examples, the new content induces a purchase of a product. In other examples, the new content increases a total amount spent on a purchase.

In some examples, the new content is provided as an output 224, such as content displayed via the display 106, printed content, audio content, or any other type of media content presentable to the individual 104. In some examples, the output 224 includes response data (e.g., response classifications, mental classifications, and the determined mental state) transmitted to the server 120. In some examples, the output 224 is in communication with the server 120 and/or the content presentation device 102 via the I/O interface 210 of the mental state determination module 202.

While an example manner of implementing the system 100 of FIG. 1 is illustrated in FIG. 2, one or more of the elements, processes and/or devices illustrated in FIG. 2 may be combined, divided, re-arranged, omitted, eliminated and/or implemented in any other way. Further, the example mental state determination module 202, the example first modality sensor 204, the example second modality sensor 206, the example Nth modality sensor 208, the example I/O interface 210, the example storage 212, the example response classifier 214, the example bin classifier 216, the example baseline generator 218, the example mental classifier 220, the example content modifier 222, the example output 224, and/or, more generally, the example systems 100, 200 of FIGS. 1 and 2 may be implemented by hardware, software, firmware and/or any combination of hardware, software and/or firmware. Thus, for example, any of the example mental state determination module 202, the example first modality sensor 204, the example second modality sensor 206, the example Nth modality sensor 208, the example I/O interface 210, the example storage 212, the example response classifier 214, the example bin classifier 216, the example baseline generator 218, the example mental classifier 220, the example content modifier 222, the example output 224 and/or, more generally, the example systems 100, 200 of FIGS. 1 and 2 could be implemented by one or more analog or digital circuit(s), logic circuits, programmable processor(s), application specific integrated circuit(s) (ASIC(s)), programmable logic device(s) (PLD(s)) and/or field programmable logic device(s) (FPLD(s)). When reading any of the apparatus or system claims of this patent to cover a purely software and/or firmware implementation, at least one of the example mental state determination module 202, the example first modality sensor 204, the example second modality sensor 206, the example Nth modality sensor 208, the example I/O interface 210, the example storage 212, the example response classifier 214, the example bin classifier 216, the example baseline generator 218, the example mental classifier 220, the example content modifier 222, the example output 224 and/or, more generally, the example systems 100, 200 is/are hereby expressly defined to include a tangible computer readable storage device or storage disk such as a memory, a digital versatile disk (DVD), a compact disk (CD), a Blu-ray disk, etc. storing the software and/or firmware. Further still, the example systems 100, 200 of FIGS. 1 and 2 may include one or more elements, processes and/or devices in addition to, or instead of, those illustrated in FIG. 2, and/or may include more than one of any or all of the illustrated elements, processes and devices.

A flowchart representative of example machine readable instructions for implementing the systems 100, 200 of FIGS. 1 and 2 is shown in FIGS. 6 and 7. In this example, the machine readable instructions comprise a program for execution by a processor such as the processor 812 shown in the example processor platform 800 discussed below in connection with FIG. 8. The program may be embodied in software stored on a tangible computer readable storage medium such as a CD-ROM, a floppy disk, a hard drive, a digital versatile disk (DVD), a Blu-ray disk, or a memory associated with the processor 812, but the entire program and/or parts thereof could alternatively be executed by a device other than the processor 812 and/or embodied in firmware or dedicated hardware. Further, although the example program is described with reference to the flowchart illustrated in FIGS. 6 and 7, many other methods of implementing the example systems 100, 200 may alternatively be used. For example, the order of execution of the blocks may be changed, and/or some of the blocks described may be changed, eliminated, or combined.

As mentioned above, the example processes of FIGS. 6 and 7 may be implemented using coded instructions (e.g., computer and/or machine readable instructions) stored on a tangible computer readable storage medium such as a hard disk drive, a flash memory, a read-only memory (ROM), a compact disk (CD), a digital versatile disk (DVD), a cache, a random-access memory (RAM) and/or any other storage device or storage disk in which information is stored for any duration (e.g., for extended time periods, permanently, for brief instances, for temporarily buffering, and/or for caching of the information). As used herein, the term tangible computer readable storage medium is expressly defined to include any type of computer readable storage device and/or storage disk and to exclude propagating signals and transmission media. As used herein, “tangible computer readable storage medium” and “tangible machine readable storage medium” are used interchangeably. Additionally or alternatively, the example processes of FIGS. 6 and 7 may be implemented using coded instructions (e.g., computer and/or machine readable instructions) stored on a non-transitory computer and/or machine readable medium such as a hard disk drive, a flash memory, a read-only memory, a compact disk, a digital versatile disk, a cache, a random-access memory and/or any other storage device or storage disk in which information is stored for any duration (e.g., for extended time periods, permanently, for brief instances, for temporarily buffering, and/or for caching of the information). As used herein, the term non-transitory computer readable medium is expressly defined to include any type of computer readable storage device and/or storage disk and to exclude propagating signals and transmission media. As used herein, when the phrase “at least” is used as the transition term in a preamble of a claim, it is open-ended in the same manner as the term “comprising” is open ended.

FIG. 6 is a flowchart representative of example machine-readable instructions 600 that may be execute for adjusting content presented to an individual 104 (using, for example, the example systems of FIGS. 1 and/or 2). The example instructions 600 begin execution when content, including audio, visual, audio-visual, and interactive content, is presented to the individual 104 via the content presentation device 102 (block 602). In an example implementation, one or more individuals is presented, via, for example, the content presentation device 102, a website including an interactive configurator. Consider, for example, the individuals using an online configurator for Adagio teas, which allows users to utilize a web interface to create custom tea blends. Alternatively, other interactive configurators could be used (e.g., Motorola MotoX Motomaker to custom design a mobile telephone, Mini auto configurator to customize an automobile, etc.). The example may also be implemented with other types of media not restricted to media intended for the purchase of customized products such as, for example, shopping for off the shelf products, gaming, entertainment, news, education, etc.

The example instructions 600 include measuring biometric and/or neurophysiological responses to content (block 604). For example, one or more of the example sensors (e.g., the camera 114, the biometric sensing clothing 116, the biometric sensing bracelet 118, and/or the first, second, and Nth modality sensors 204, 206, 208) measures the response of the individual 104 to the content, which may include a biometric response, a neurophysiological response, and/or a behavioral response. In some examples, a first response to first content is measured by the first modality sensor 204 during a first time frame and a second response to first content is measured by the second modality sensor 206 during the first time frame. Additionally, in some examples, the first modality sensor 204 measures a third response of the individual to first content during a second time frame and the second modality sensor 206 measures a fourth response of the individual to the first content during a second time frame. In the example implementation, sensors collected data related to GSR, FAC, eye tracking and pupil dilation for the individuals exposed to the Adagio tea configurator. The responses are averaged over a time period (block 606) using, for example, the response classifier 214 to average the responses (e.g., heart rate, pupil dilation, GSR, etc.) of each sensor 204, 206, 208 over a first time frame.

For example, the responses of each of the individuals were monitored for the duration of the exposure to various images, text, displays, and/or other options presented via the Adagio tea configurator. The duration included multiple time frames. The responses of the individual were averaged for each of the time frames. For example, a sensor detected FAC may detect a furrowed brow and a tight lip during a time window. These detected features could change over the duration of the time window, and an average across the window in determined.

The example instructions 600 include comparing the average of each response to a threshold (block 608). For example, the response classifier 214 compares the average response values to respective thresholds corresponding to the sensors 204, 206, 208 to classify each response (e.g., high heart rate, low heart rate, low GSR, etc.). In some examples, a first response is compared to a first threshold and a second response is compared to a second threshold. In some examples, the first threshold or the second threshold is based on a first baseline determined for a first time frame. In some such examples, the first baseline is adjusted to a second baseline based on the third response and/or the fourth response. In some examples, the first threshold is adjusted to a third threshold and/or the second threshold is adjusted to a fourth threshold. Additionally, in some examples, a third response is compared to a third threshold and a fourth response is compared to a fourth threshold.

For example, in the Adagio tea implementation described above, the individuals using the configurator may be presented with 30 images and 4 video clips to establish a baseline and/or threshold to which the responses measured during the exposure to the Adagio tea configurator are compared. The individuals' responses from one or more sensors (including for example GSR, FAC, and/or pupillary dilation) are compared to the thresholds over time. For example, the average FAC response (based on the furrowed brow and tight lip mentioned above) is compared to a threshold value related to features detected via FACs sensors to determine a relative level of, for example, furrowed brows and tight lips. In addition, the system operating the configurator may, at times, determine that a baseline and/or threshold may have to be adjusted, as described above and below with respect to FIG. 7.

Each response is placed in a bin based on the comparison (block 610). In addition, the example bin classifier 216 places each response into a respective bin (e.g., high, medium, low) based on the comparison to the threshold. The response classifier 214 determines a response classification (e.g., high GSR, low heart rate, low pupil dilation, etc.) for each response based on the comparison of the average response value(s) to the threshold(s) and/or the bin(s) in which each response is placed.

For example, the responses of the individuals using the Adagio tea configurator are placed in high or low GSR bin; high, medium, or low FAC bins; and high, medium, or low pupillary dilation bins and/or other bins relative to the biometric responses detected from the individual while presented with the configurator. For example, a low FAC bin may include negative responses such as, for example, those identifiable by furrowed brows and tight lips.

The example instructions 600 include assigning a weight to each response (block 612). For example, the response classifier 214 assigns a weight to each response corresponding to the amount each response contributes to the determined mental state of the individual 104. For example, if three response classifications are available, each response classification may be weighted as 33%. In another example implementation, each of the responses are given a weight corresponding to the contribution of each response to the determined mental state. For example, pupil dilation data can be adversely affected due to changing lighting when viewing dynamic media and, thus, the weighting for pupil dilation may be less than the weighting for each of GSR, FAC, and/or eye tracking, etc.

The example instructions 600 also determine first response classification for each response over a first time period (block 614) and second response classification of each response over a second time period (block 616). For example, the response classifier 214 of FIG. 2 may be used to provide these determinations based on the comparison of the average response to a threshold (block 608) and/or a bin (block 610) in which the response was placed. In some examples, a first response classification is determined based on a first comparison of the first response and a first threshold and a second response classification is determined based on a second comparison of the second response to a second threshold. Additionally, in some examples, a third response classification is determined based on a third comparison of the third response data to a third threshold and a fourth response classification is determined based on a fourth comparison of the fourth response to a fourth threshold.

In the Adagio tea example implementation, responses are measured over numerous time periods, and response classifications are determined for each time period by comparing the responses to relevant thresholds to detect fluctuations or changes in the response of the individual. For example, based on the comparison of the FACs data (e.g., the furrowed brows and tight lips) to the thresholds and/or bin data, it may be determined that the responses during the measured time periods if low or negative.

In this example, the instructions 600 combine classifications of each response to create a mental classification (block 618). For example, the mental classifier 220 determines a mental classification (e.g., frustration, confusion, boredom, etc.) for a time segment by combining response classifications from the first time period and/or the second time period. In some examples, a first mental classification of the individual is determined based on combining the first response classification and the second response classification. Additionally, in some examples, a second mental classification is determined based on combining the third response classification and the fourth response classification. In the example implementation, an individual with response classifications including high GSR, high pupil dilation, high negative FAC, and low positive FAC was determined to have a mental classification of frustrated.

In addition, the example instructions 600 are used to identify consecutive similar mental classifications (block 620). For example, the mental state determination module 202 of FIG. 2 assess the mental classifications and identifies consecutive mental classifications that are similar (e.g., two time periods during which the mental classification is similar). The example instructions 600 use the consecutive similar mental classification to determine the mental state (e.g., frustration, confusion, boredom, etc.) of the individual (block 622) using, for example the mental state determination module 202 of FIG. 2. In some examples, a mental state of a user is determined based on a degree of similarity between the first mental classification and the second mental classification. In the Adagio tea example implementation, an individual having a mental classification of frustrated for at least three consecutive time periods (for example) is assigned a mental state of frustrated.

Based on the determined mental state, the instructions are further executed to determine whether the mental state should be adjusted (block 624) to, for example, increase the positivity, decrease negativity, increase intensity, heighten a concentration and/or otherwise make a change to the mental state. For example, any individual operating the Adagio tea configurator who is experiencing frustration would be identified as a candidate in need of a mental state adjustment.

If it is determined that the mental state is to be adjusted, the instructions 600 include modifying the content (block 626). For example, the content modifier 222 of FIG. 2 may be used to adjust the content presented to the individual 104. For example, if the mental state indicates the individual is frustrated, the content modifier may display additional content, such as a helpful video, a coupon, quieter or louder audio, brighter or dimmer display brightness, more or less display items, etc. In some examples, the content modifies the first content to include second content and/or replaces the first content with second content based on the mental state. For example, the new or modified content presented to the individual 104 during the tea configuration process may also include, for example, a reduced choice of tea flavors to choose from to help the individual 104 decide, a suggested flavor of tea, a free gift (e.g., a tea infuser), a tutorial video, a suggested popular blend, etc. Additionally, in the example implementation, the individuals are presented with the option to swap the created tea blend for the tea blend of the month (e.g., a forced choice) and to add on items, such as cookies and a personalized mug (e.g., upsell) at the checkout.

After content has been modified (block 626), the control returns to block 602 and the modified content is presented to the individual and the example instructions 600 continue with the data gathering and analysis disclosed above. However, if it is determined that the mental state does not need to be adjusted (block 624), the example instructions are also used to determine whether or not to continue monitoring the individual (block 628). For example, if the mental state determination module 202 decides to continue monitoring the individual 104, control returns to block 604 and monitoring continues. However, if it is determined that monitoring is not to continue (block 628), monitoring ceases and the process 600 is complete (block 630). In the example implementation, the system continued to monitor the individual through the entire experience with the tea configurator and the process was designated as complete after the individual completed the checkout process. The results of the particular example implementation showed a positive impact on the amount of money spent by individuals receiving new or modified content based on the determined mental state (i.e., the individuals in the minimal and maximal adaptation groups spent more than the individuals in the random and control groups), with the maximal adaptation spending a slightly higher amount.

FIG. 7 is a flowchart representative of example machine-readable instructions or process 700 that may be executed for adjusting a baseline and/or threshold (using, for example, the example systems of FIGS. 1 and/or 2). The example instructions 700 include presenting content to one of more individuals that does not include a stimulus or target material (e.g., neutral or background media) (block 702). For example, the example presentation device 102 of FIG. 1 may be used to present content to an individual including, for example, a website containing a news article, an entertainment video, ambient audio etc.

The example instructions 700 include monitoring biometric responses (block 704). For example, one or more of the example sensors (e.g., the camera 114, the biometric sensing clothing 116, the biometric sensing bracelet 118, and/or the first, second, and Nth modality sensors 204, 206, 208) measures the response of the individual 104 to the content, which may include a biometric response, a neurophysiological response, and/or a behavioral response.

A baseline response is determined (block 706), using for example the baseline generator 218 if FIG. 2. The baseline may be used to identify biometric responses of the individual when in an inactive, unengaged, or unstimulated state (e.g., a passive state). The example instructions 700 also include establishing a threshold (block 708). The threshold may be determined by one of the components of the example system 200 of FIG. 2 (e.g., the response classifier 214 and/or baseline generator 218) in some examples, and in other examples, the threshold may be imported into the example system 200. The threshold values used in the example process 700 are set to indicate when a biometric response has deviated from the individual's baseline by an amount sufficient to signify that a change in a response has occurred.

The example instructions 700 also include presenting the individual with content that includes stimulus and/or target material (block 710). For example, the presentation device 102 of FIG. 1 maybe used to present a website (such as, for example, the tea configurator detailed above) to an individual. Further biometric responses are monitored (block 712) and compared to the current baseline and/or threshold (block 714).

The example instructions 700 are executed to determine if a period of time elapses in which the threshold has not been triggered (block 716). Triggering the threshold may mean, for example, meeting a threshold, crossing or exceeding a threshold, falling without or outside of a threshold range, etc. For example, the example system 200 analyzes the monitored biometric responses over time and continually compares the responses to the threshold, which was established in relation to the individual's baseline. In some examples, the individual's heart rate may be monitored to determine if the heart rate moves higher than 10 bmp over a baseline heart rate, or if the heart exceeds an absolute value change, or if the heart rate passes 80 bmp, and/or any other suitable or desired metrics. If the threshold has been triggered within the established time period, the individual's responses are continued to be monitored (block 712).

However, the threshold has not been triggered within the set time period (block 716), the example instructions 700 are executed to determine if the content has been modified (block 718) and, if not, content is modified (block 720), presented to the individual (block 710), and monitoring continues (block 712). The content may be modified, for example, in accordance with the example systems 100, 200 of FIGS. 1 and 2 and/or the process 600 of FIG. 6.

If the content has been modified (block 718), the example instructions 700 adjust the individual's baseline and/or reestablishes the threshold relative to the baseline (block 722) using, for example, the example system 200 including the baseline generator 218 as disclosed above. For example, if the individual is experiencing frustration and adjustments are made the content to change the individual's biometric responses (and, thus, mental state), but the system continues to read the individual's response as frustrated, there may be an indication that the adjusted content is not sufficient to change the individual's response to a more positive response.

Additionally or alternatively, this may be an indication that the threshold set, with respect to the baseline, is insufficient to detect a change in response. For example, if an individual has a baseline heart rate of 75 bpm and a threshold is set to a 5 bpm change (plus or minus), the change may determine when a person is experiencing boredom or frustration. If the person has a change of 10 bpm, the threshold has been crossed. There may be a desire to present modified content to the individual to change the response back to a positive response as indicated by the heart rate crossing the threshold back toward the 75 bpm baseline. New content may be provided, which alters the individual's 10 bmp change to 8 bmp but does not cross the 5 bmp threshold. This change indicates that the altered content is effective in changing the responses to the desired response. However, the change is not enough to trigger threshold and, therefore, goes undetected. This may cause the content provider to abandon the content modification, may ultimately be effective for changing the response to the desired response, or cause the content provider to overcompensate resulting in further and unnecessary modification of the content. With the present example systems and processes, the threshold may be adjusted to, for example a change of 2 bmp, for a more fine detection of responses changes. This advancement provides the content with enhanced detection capabilities and advanced knowledge of the effectiveness in content modification in causes an individual to have a desired response.

In addition, there are examples in which the baseline itself is to be changed. For example, if a content provider would like to know when an individual has a change in heart rate when the measurements already exceed the threshold and/or continuously exceed the threshold for a period of time, the baseline is adjusted to reflect the changes in heart rate at levels higher than the previous baseline. In some examples, the baseline may be changed based on task. A low stress task (e.g., buying a toothbrush) may have a lower baseline for heart rate than a high stress task (e.g., configuring a car) because the individual is more likely have a higher heart rate while performing the higher stress task and would likely continuously exceed a baseline for a lower stress task unless the baseline is adjusted according to the task. In some examples, the length of time for which the task is performed affects the change in the baseline.

FIG. 8 is a block diagram of an example processor platform 800 capable of executing the instructions of FIGS. 6 and 7 to implement the apparatus and systems of FIGS. 1 and 2 including for example, the mental state determination module 202, the response classifier 214, the bin classifier 216, the baseline generator 218 and the mental classifier 220 and/or content modifier 222 of FIG. 2. The processor platform 800 can be, for example, a server, a personal computer, a mobile device (e.g., a cell phone, a smart phone), a personal digital assistant (PDA), an Internet appliance, a DVD player, a CD player, a digital video recorder, a Blu-ray player, a gaming console, a personal video recorder, a set top box, or any other type of computing device.

The processor platform 800 of the illustrated example includes a processor 812. The processor 812 of the illustrated example is hardware. For example, the processor 812 can be implemented by one or more integrated circuits, logic circuits, microprocessors or controllers from any desired family or manufacturer.

The processor 812 of the illustrated example includes a local memory 813 (e.g., a cache). The processor 812 of the illustrated example is in communication with a main memory including a volatile memory 814 and a non-volatile memory 816 via a bus 818. The volatile memory 814 may be implemented by Synchronous Dynamic Random Access Memory (SDRAM), Dynamic Random Access Memory (DRAM), RAMBUS Dynamic Random Access Memory (RDRAM) and/or any other type of random access memory device. The non-volatile memory 816 may be implemented by flash memory and/or any other desired type of memory device. Access to the main memory 814, 816 is controlled by a memory controller.

The processor platform 800 of the illustrated example also includes an interface circuit 820. The interface circuit 820 may be implemented by any type of interface standard, such as an Ethernet interface, a universal serial bus (USB), and/or a PCI express interface.

In the illustrated example, one or more input devices 822 are connected to the interface circuit 820. The input device(s) 822 permit(s) a user to enter data and commands into the processor 812. The input device(s) can be implemented by, for example, an audio sensor, a microphone, a camera (still or video), a keyboard, a button, a mouse, a touchscreen, a track-pad, a trackball, isopoint and/or a voice recognition system.

One or more output devices 824 are also connected to the interface circuit 820 of the illustrated example. The output devices 824 can be implemented, for example, by display devices (e.g., a light emitting diode (LED), an organic light emitting diode (OLED), a liquid crystal display, a cathode ray tube display (CRT), a touchscreen, a tactile output device, a light emitting diode (LED), a printer and/or speakers). The interface circuit 820 of the illustrated example, thus, typically includes a graphics driver card, a graphics driver chip or a graphics driver processor.

The interface circuit 820 of the illustrated example also includes a communication device such as a transmitter, a receiver, a transceiver, a modem and/or network interface card to facilitate exchange of data with external machines (e.g., computing devices of any kind) via a network 826 (e.g., an Ethernet connection, a digital subscriber line (DSL), a telephone line, coaxial cable, a cellular telephone system, etc.).

The processor platform 800 of the illustrated example also includes one or more mass storage devices 828 for storing software and/or data. Examples of such mass storage devices 828 include floppy disk drives, hard drive disks, compact disk drives, Blu-ray disk drives, RAID systems, and digital versatile disk (DVD) drives.

The coded instructions 832 of FIG. 8 may be stored in the mass storage device 828, in the volatile memory 814, in the non-volatile memory 816, and/or on a removable tangible computer readable storage medium such as a CD or DVD.

From the foregoing, it will appreciate that the above disclosed methods, apparatus and articles of manufacture are operative to provide the individual with a better experience when interacting with media content, including websites, by altering content and/or presenting new content based on a mental state of the individual while viewing and/or interacting with the content.

Although certain example methods, apparatus and articles of manufacture have been disclosed herein, the scope of coverage of this patent is not limited thereto. On the contrary, this patent covers all methods, apparatus and articles of manufacture fairly falling within the scope of the claims of this patent.

Claims

1. A system comprising:

a first sensor to measure a first response of an individual to first content during a first time frame and a second response of the individual to the first content during a second time frame, the first sensor including a pupil dilation sensor;

a second sensor to measure a third response of the individual to the first content during the first time frame and a fourth response of the individual to the first content during the second time frame; and

a processor to:

generate a cognitive load index based on data from the pupil dilation sensor, the cognitive load index representative of how much of an information processing capacity of the individual is being used;

determine a first mental classification of the individual based on (1) a first comparison of the first response to a first threshold and (2) a second comparison of the third response to a second threshold;

determine a second mental classification of the individual based on (1) a third comparison of the second response to a third threshold and (2) a fourth comparison of the fourth response to a fourth threshold;

determine a mental state of the individual based on a degree of similarity between the first mental classification and the second mental classification; and

at least one of modify the first content to include second content or replace the first content with the second content based on the mental state.

2. The system of claim 1, wherein the second sensor includes a galvanic skin response sensor.

3. The system of claim 1, wherein the processor is to modify the first content based on the cognitive load index.

4. The system of claim 1, wherein the second time frame partially overlaps the first time frame.

5. The system of claim 1 further including a third sensor to:

measure a fifth response of the individual to the first content during the first time frame; and

measure a sixth response of the individual to the first content during the second time frame;

the processor to:

determine the first mental classification of the individual based, in part, on a fifth comparison of the fifth response with a fifth threshold; and

determine the second mental classification of the individual based, in part, on a sixth comparison of the sixth response with a sixth threshold.

6. The system of claim 5, wherein the third sensor includes at least one of a facial action coding sensor or an eye tracking sensor.

7. The system of claim 1, wherein the second content is to increase a positivity level of the mental state.

8. The system of claim 1, wherein the second content is to at least one of induce a purchase by the individual or increase a total spend amount by the individual.

9. The system of claim 1, wherein the first content is a website and the second content is to increase a time spent by the individual at the website.

10. The system of claim 1, wherein the first content is a website and the second content is to change the mental state to decrease a level of frustration experienced by the individual.

11. The system of claim 1, wherein the processor is to adjust at least one of the first threshold, the second threshold, the third threshold, or the fourth threshold over time.

12. The system of claim 1, wherein the processor is to generate at least one of the first threshold, the second threshold, the third threshold, or the fourth threshold based on at least one of the first response, the second response, the third response, or the fourth response.

13. A tangible computer readable storage medium comprising instructions that, when executed, cause a machine to at least:

determine a first mental classification of an individual based on (1) a first comparison of a first response of the individual to first content to a first threshold and (2) a second comparison of a second response of the individual to the first content to a second threshold, the first response measured via a first modality during a first time frame, and the second response measured via a second modality during the first time frame, the second modality including sensing pupil dilation;

generate a cognitive load index based on pupil dilation data, the cognitive load index representative of how much of an information processing capacity of the individual is being used;

determine a second mental classification of the individual based on (1) a third comparison of a third response of the individual to the first content to a third threshold and (2) a fourth comparison of a fourth response of the individual to the first content to a fourth threshold, the third response measured via the first modality during a second time frame, and the fourth response measured during the second time frame;

determine a mental state of the individual based on a degree of similarity between the first mental classification and the second mental classification; and

at least one of modify the first content to include second content or replace the first content with the second content based on the mental state.

14. The tangible computer readable storage medium of claim 13 wherein the instructions, when executed, further cause the machine to modify the first content based on the cognitive load index and the mental state.

15. The tangible computer readable storage medium of claim 13, wherein the first content is a website and the second content is to at least one of an increase in time spent by the individual at the website or a change in the mental state to decrease a level of frustration experience by the individual.

16. The tangible computer readable storage medium of claim 13, wherein the instructions, when executed, further cause the machine to adjust at least one of the first threshold, the second threshold, the third threshold, or the fourth threshold over time.

17. The tangible computer readable storage medium of claim 13, wherein the instructions, when executed, further cause the machine to generate at least one of the first threshold, the second threshold, the third threshold, or the fourth threshold based on at least one of the first response, the second response, the third response, or the fourth response.

18. An apparatus comprising:

means for measuring a first response of an individual to first content during a first time frame and a second response of the individual to the first content during a second time frame, the means for measuring the first response and the second response including sensing pupil dilation;

means for measuring a third response of the individual to the first content during the first time frame and a fourth response of the individual to the first content during the second time frame;

means for analyzing responses, the response analyzing means to:

generate a cognitive load index based on pupil dilation data, the cognitive load index representative of how much of an information processing capacity of the individual is being used;

determine a first mental classification of the individual based on (1) a first comparison of the first response to a first threshold and (2) a second comparison of the third response to a second threshold; and

determine a second mental classification of the individual based on (1) a third comparison of the second response to a third threshold and (2) a fourth comparison of the fourth response to a fourth threshold;

means for determining a mental state of the individual based on a degree of similarity between the first mental classification and the second mental classification; and

means for at least one of modifying the first content to include second content or replacing the first content with the second content based on the mental state.